ICLR 2025

3,703 papers

X-Sample Contrastive Loss: Improving Contrastive Learning with Sample Similarity Graphs

Vlad Sobal, Mark Ibrahim, Randall Balestriero, Vivien Cabannes, Diane Bouchacourt

Energy-Weighted Flow Matching for Offline Reinforcement Learning

Shiyuan Zhang, Weitong ZHANG, Quanquan Gu

Quality over Quantity in Attention Layers: When Adding More Heads Hurts

Noah Amsel, Gilad Yehudai, Joan Bruna

DeciMamba: Exploring the Length Extrapolation Potential of Mamba

Assaf Ben-Kish, Itamar Zimerman, Shady Abu-Hussein, Nadav Cohen, Amir Globerson

Image and Video Tokenization with Binary Spherical Quantization

Yue Zhao, Yuanjun Xiong, Philipp Kraehenbuehl

PEAR: Primitive Enabled Adaptive Relabeling for Boosting Hierarchical Reinforcement Learning

Utsav Singh, Vinay P. Namboodiri

Last Iterate Convergence of Incremental Methods as a Model of Forgetting

Xufeng Cai, Jelena Diakonikolas

Cybench: A Framework for Evaluating Cybersecurity Capabilities and Risks of Language Models

Andy K Zhang, Neil Perry, Riya Dulepet, Joey Ji, Celeste Menders

Proxy Denoising for Source-Free Domain Adaptation

Song Tang, Wenxin Su, Yan Gan, Mao Ye, Jianwei Dr. Zhang

Distributional Associations vs In-Context Reasoning: A Study of Feed-forward and Attention Layers

Lei Chen, Joan Bruna, Alberto Bietti

Permute-and-Flip: An optimally stable and watermarkable decoder for LLMs

Xuandong Zhao, Lei Li, Yu-Xiang Wang

For Better or For Worse? Learning Minimum Variance Features With Label Augmentation

Muthu Chidambaram, Rong Ge

Discovering Temporally Compositional Neural Manifolds with Switching Infinite GPFA

Changmin Yu, Maneesh Sahani, Máté Lengyel

Credal Wrapper of Model Averaging for Uncertainty Estimation in Classification

Kaizheng Wang, Fabio Cuzzolin, Keivan Shariatmadar, David Moens, Hans Hallez

DOPL: Direct Online Preference Learning for Restless Bandits with Preference Feedback

GUOJUN XIONG, Ujwal Dinesha, Debajoy Mukherjee, Jian Li, Srinivas Shakkottai

Stabilizing Reinforcement Learning in Differentiable Multiphysics Simulation

Eliot Xing, Vernon Luk, Jean Oh

OGBench: Benchmarking Offline Goal-Conditioned RL

Seohong Park, Kevin Frans, Benjamin Eysenbach, Sergey Levine

Generalization in VAE and Diffusion Models: A Unified Information-Theoretic Analysis

Qi Chen, Jierui Zhu, Florian Shkurti

Robustness Inspired Graph Backdoor Defense

Zhiwei Zhang, Minhua Lin, Junjie Xu, Zongyu Wu, Enyan Dai

DuoAttention: Efficient Long-Context LLM Inference with Retrieval and Streaming Heads

Guangxuan Xiao, Jiaming Tang, Jingwei Zuo, Junxian Guo, Shang Yang

Scale-Free Graph-Language Models

Jianglin Lu, Yixuan Liu, Yitian Zhang, Yun Fu

Judge Decoding: Faster Speculative Sampling Requires Going Beyond Model Alignment

Gregor Bachmann, Sotiris Anagnostidis, Albert Pumarola, Markos Georgopoulos, Artsiom Sanakoyeu

One Step Diffusion via Shortcut Models

Kevin Frans, Danijar Hafner, Sergey Levine, Pieter Abbeel

Reinforcement learning with combinatorial actions for coupled restless bandits

Lily Xu, Bryan Wilder, Elias Boutros Khalil, Milind Tambe

LR0.FM: Low-Res Benchmark and Improving robustness for Zero-Shot Classification in Foundation Models

Priyank Pathak, Shyam Marjit, Shruti Vyas, Yogesh S Rawat

Agree to Disagree: Demystifying Homogeneous Deep Ensembles through Distributional Equivalence

Yipei Wang, Xiaoqian Wang

InstaTrain: Adaptive Training via Ultra-Fast Natural Annealing within Dynamical Systems

Chuan Liu, Ruibing Song, Chunshu Wu, Pouya Haghi, Tong Geng

Stochastic Polyak Step-sizes and Momentum: Convergence Guarantees and Practical Performance

Dimitris Oikonomou, Nicolas Loizou

Scalable Universal T-Cell Receptor Embeddings from Adaptive Immune Repertoires

Paidamoyo Chapfuwa, Ilker Demirel, Lorenzo Pisani, Javier Zazo, Elon Portugaly

NRGBoost: Energy-Based Generative Boosted Trees

João Bravo

Diff-PIC: Revolutionizing Particle-In-Cell Nuclear Fusion Simulation with Diffusion Models

Chuan Liu, Chunshu Wu, shihui cao, Mingkai Chen, James Chenhao Liang

Learning to Steer Markovian Agents under Model Uncertainty

Jiawei Huang, Vinzenz Thoma, Zebang Shen, Heinrich H. Nax, Niao He

Sharpness-Aware Minimization: General Analysis and Improved Rates

Dimitris Oikonomou, Nicolas Loizou

Looking into User’s Long-term Interests through the Lens of Conservative Evidential Learning

Dingrong Wang, Krishna Prasad Neupane, Ervine Zheng, Qi Yu

Building Math Agents with Multi-Turn Iterative Preference Learning

Wei Xiong, Chengshuai Shi, Jiaming Shen, Aviv Rosenberg, Zhen Qin

A Causal Lens for Learning Long-term Fair Policies

Jacob Lear, Lu Zhang

Competing Large Language Models in Multi-Agent Gaming Environments

Jen-tse Huang, Eric John Li, Man Ho Lam, Tian Liang, Wenxuan Wang

Training Nonlinear Transformers for Chain-of-Thought Inference: A Theoretical Generalization Analysis

Hongkang Li, Songtao Lu, Pin-Yu Chen, Xiaodong Cui, Meng Wang

Boltzmann Semantic Score: A Semantic Metric for Evaluating Large Vision Models Using Large Language Models

Ali Khajegili Mirabadi, Katherine Rich, Hossein Farahani, Ali Bashashati

Varying Shades of Wrong: Aligning LLMs with Wrong Answers Only

Jihan Yao, Wenxuan Ding, Shangbin Feng, Lucy Lu Wang, Yulia Tsvetkov

Aligning Generative Denoising with Discriminative Objectives Unleashes Diffusion for Visual Perception

Ziqi Pang, Xin Xu, Yu-Xiong Wang

Unlocking the Power of Function Vectors for Characterizing and Mitigating Catastrophic Forgetting in Continual Instruction Tuning

Gangwei Jiang, Caigao JIANG, Zhaoyi Li, Siqiao Xue, Jun Zhou

Optimal Learning of Kernel Logistic Regression for Complex Classification Scenarios

Hongwei Wen, Annika Betken, Hanyuan Hang

OmniSep: Unified Omni-Modality Sound Separation with Query-Mixup

Xize Cheng, Siqi Zheng, Zehan Wang, Minghui Fang, Ziang Zhang

Duoduo CLIP: Efficient 3D Understanding with Multi-View Images

Han-Hung Lee, Yiming Zhang, Angel X Chang

Contractive Dynamical Imitation Policies for Efficient Out-of-Sample Recovery

Amin Abyaneh, Mahrokh Ghoddousi Boroujeni, Hsiu-Chin Lin, Giancarlo Ferrari-Trecate

Detecting Backdoor Samples in Contrastive Language Image Pretraining

Hanxun Huang, Sarah Monazam Erfani, Yige Li, Xingjun Ma, James Bailey

How DNNs break the Curse of Dimensionality: Compositionality and Symmetry Learning

Arthur Jacot, Seok Hoan Choi, Yuxiao Wen

CLIBD: Bridging Vision and Genomics for Biodiversity Monitoring at Scale

ZeMing Gong, Austin Wang, Xiaoliang Huo, Joakim Bruslund Haurum, Scott C. Lowe

Learning the Optimal Stopping for Early Classification within Finite Horizons via Sequential Probability Ratio Test

Akinori F. Ebihara, Taiki Miyagawa, Kazuyuki Sakurai, Hitoshi Imaoka

Improved Finite-Particle Convergence Rates for Stein Variational Gradient Descent

Sayan Banerjee, Krishna Balasubramanian, Promit Ghosal

Catastrophic Failure of LLM Unlearning via Quantization

Zhiwei Zhang, Fali Wang, Xiaomin Li, Zongyu Wu, Xianfeng Tang

Fragment and Geometry Aware Tokenization of Molecules for Structure-Based Drug Design Using Language Models

Cong Fu, Xiner Li, Blake Olson, Heng Ji, Shuiwang Ji

Deep MMD Gradient Flow without adversarial training

Alexandre Galashov, Valentin De Bortoli, Arthur Gretton

Score Forgetting Distillation: A Swift, Data-Free Method for Machine Unlearning in Diffusion Models

Tianqi Chen, Shujian Zhang, Mingyuan Zhou

Partial Gromov-Wasserstein Metric

Yikun Bai, Rocio Diaz Martin, Abihith Kothapalli, Hengrong Du, Xinran Liu

Guided Score identity Distillation for Data-Free One-Step Text-to-Image Generation

Mingyuan Zhou, Zhendong Wang, Huangjie Zheng, Hai Huang

How many samples are needed to train a deep neural network?

Pegah Golestaneh, Mahsa Taheri, Johannes Lederer

Dynamic Neural Fortresses: An Adaptive Shield for Model Extraction Defense

Siyu Luan, Zhenyi Wang, Li Shen, Zonghua Gu, Chao Wu

Multimodal Unsupervised Domain Generalization by Retrieving Across the Modality Gap

Christopher Liao, Christian So, Theodoros Tsiligkaridis, Brian Kulis

Robust Gymnasium: A Unified Modular Benchmark for Robust Reinforcement Learning

shangding gu, Laixi Shi, Muning Wen, Ming Jin, Eric Mazumdar

Symbolic regression via MDLformer-guided search: from minimizing prediction error to minimizing description length

Zihan Yu, Jingtao Ding, Yong Li, Depeng Jin

Adversarial Latent Feature Augmentation for Fairness

Hoin Jung, Junyi Chai, Xiaoqian Wang

Learning Multi-Index Models with Neural Networks via Mean-Field Langevin Dynamics

Alireza Mousavi-Hosseini, Denny Wu, Murat A Erdogdu

Gaussian Ensemble Belief Propagation for Efficient Inference in High-Dimensional, Black-box Systems

Dan MacKinlay, Russell Tsuchida, Daniel Edward Pagendam, Petra Kuhnert

Faster Inference of Flow-Based Generative Models via Improved Data-Noise Coupling

Aram Davtyan, Leello Tadesse Dadi, Volkan Cevher, Paolo Favaro

Tractable Multi-Agent Reinforcement Learning through Behavioral Economics

Eric Mazumdar, Kishan Panaganti, Laixi Shi

Test-Time Ensemble via Linear Mode Connectivity: A Path to Better Adaptation

Byungjai Kim, Chanho Ahn, Wissam J. Baddar, Kikyung Kim, Huijin Lee

Multimodal Large Language Models for Inverse Molecular Design with Retrosynthetic Planning

Gang Liu, Michael Sun, Wojciech Matusik, Meng Jiang, Jie Chen

Learning General-purpose Biomedical Volume Representations using Randomized Synthesis

Neel Dey, Benjamin Billot, Hallee E. Wong, Clinton Wang, Mengwei Ren

Leveraging Driver Field-of-View for Multimodal Ego-Trajectory Prediction

M. Eren Akbiyik, Nedko Savov, Danda Pani Paudel, Nikola Popovic, Christian Vater

Calibrating Expressions of Certainty

Peiqi Wang, Barbara D. Lam, Yingcheng Liu, Ameneh Asgari-Targhi, Rameswar Panda

Repulsive Latent Score Distillation for Solving Inverse Problems

Nicolas Zilberstein, Morteza Mardani, Santiago Segarra

Exact Community Recovery under Side Information: Optimality of Spectral Algorithms

Julia Gaudio, Nirmit Joshi

SyllableLM: Learning Coarse Semantic Units for Speech Language Models

Alan Baade, Puyuan Peng, David Harwath

Differentiable Causal Discovery for Latent Hierarchical Causal Models

Parjanya Prajakta Prashant, Ignavier Ng, Kun Zhang, Biwei Huang

ObscuraCoder: Powering Efficient Code LM Pre-Training Via Obfuscation Grounding

Indraneil Paul, Haoyi Yang, Goran Glavaš, Kristian Kersting, Iryna Gurevych

Post-hoc Reward Calibration: A Case Study on Length Bias

Zeyu Huang, Zihan Qiu, Zili Wang, Edoardo Ponti, Ivan Titov

Fully-inductive Node Classification on Arbitrary Graphs

Jianan Zhao, Zhaocheng Zhu, Mikhail Galkin, Hesham Mostafa, Michael M. Bronstein

Exploiting Structure in Offline Multi-Agent RL: The Benefits of Low Interaction Rank

Wenhao Zhan, Scott Fujimoto, Zheqing Zhu, Jason D. Lee, Daniel Jiang

Interference Among First-Price Pacing Equilibria: A Bias and Variance Analysis

Luofeng Liao, Christian Kroer, Sergei Leonenkov, Okke Schrijvers, Liang Shi

To CoT or not to CoT? Chain-of-thought helps mainly on math and symbolic reasoning

Zayne Rea Sprague, Fangcong Yin, Juan Diego Rodriguez, Dongwei Jiang, Manya Wadhwa

Global Well-posedness and Convergence Analysis of Score-based Generative Models via Sharp Lipschitz Estimates

Connor Mooney, Zhongjian Wang, Jack Xin, Yifeng Yu

Conformal Structured Prediction

Botong Zhang, Shuo Li, Osbert Bastani

EmbodiedSAM: Online Segment Any 3D Thing in Real Time

Xiuwei Xu, Huangxing Chen, Linqing Zhao, Ziwei Wang, Jie Zhou

Discovering Clone Negatives via Adaptive Contrastive Learning for Image-Text Matching

Renjie Pan, Jihao Dong, Hua Yang

DEEM: Diffusion models serve as the eyes of large language models for image perception

Run Luo, Yunshui Li, Longze Chen, Wanwei He, Ting-En Lin

Machine Unlearning via Simulated Oracle Matching

Kristian Georgiev, Roy Rinberg, Sung Min Park, Shivam Garg, Andrew Ilyas

OCCAM: Towards Cost-Efficient and Accuracy-Aware Classification Inference

Dujian Ding, Bicheng Xu, Laks V. S. Lakshmanan

Temporal Difference Learning: Why It Can Be Fast and How It Will Be Faster

Patrick Schnell, Luca Guastoni, Nils Thuerey

Overcoming False Illusions in Real-World Face Restoration with Multi-Modal Guided Diffusion Model

Keda Tao, Jinjin Gu, Yulun Zhang, Xiucheng Wang, Nan Cheng

Distribution-Specific Agnostic Conditional Classification With Halfspaces

Jizhou Huang, Brendan Juba

MallowsPO: Fine-Tune Your LLM with Preference Dispersions

Haoxian Chen, HANYANG ZHAO, Henry Lam, David Yao, Wenpin Tang

Task Descriptors Help Transformers Learn Linear Models In-Context

Ruomin Huang, Rong Ge

REvolve: Reward Evolution with Large Language Models using Human Feedback

Rishi Hazra, Alkis Sygkounas, Andreas Persson, Amy Loutfi, Pedro Zuidberg Dos Martires

Towards Generalization Bounds of GCNs for Adversarially Robust Node Classification

Wen Wen, Han Li, Tieliang Gong, Hong Chen

Indirect Gradient Matching for Adversarial Robust Distillation

Hongsin Lee, Seungju Cho, Changick Kim

Synthetic continued pretraining

Zitong Yang, Neil Band, Shuangping Li, Emmanuel Candes, Tatsunori Hashimoto

JudgeBench: A Benchmark for Evaluating LLM-Based Judges

Sijun Tan, Siyuan Zhuang, Kyle Montgomery, William Yuan Tang, Alejandro Cuadron

MOS: Model Synergy for Test-Time Adaptation on LiDAR-Based 3D Object Detection

Zhuoxiao Chen, Junjie Meng, Mahsa Baktashmotlagh, Yonggang Zhang, Zi Huang